www.patreon.com Open in urlscan Pro
2606:4700::6810:731  Public Scan

Form analysis
1 forms found in the DOM

GET /search

<form action="/search" method="GET" role="search" class="sc-iNGGcK bOJoHC" data-airgap-id="58">
  <div class="sc-jeraig giOguN">
    <div class="sc-bkkeKt eXvPyy">
      <div aria-expanded="false" aria-haspopup="true" aria-label="[object Object]" data-tag="menuToggleDiv" class="sc-AjmGg duYiDU">
        <div class="sc-bkkeKt bfvFyI">
          <div class="sc-nVkyK efwArR">
            <div aria-hidden="true" class="sc-jRQBWg jVEoqB"><svg viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
                <path
                  d="m20.006 17.354-.805-.804-.803-.804c-.661-.661-.988-.967-1.079-1.33-.09-.364.054-.785.336-1.677A7.422 7.422 0 0 0 18 10.5c0-2.071-.84-3.946-2.197-5.303A7.477 7.477 0 0 0 10.5 3c-2.071 0-3.946.84-5.303 2.197A7.477 7.477 0 0 0 3 10.5c0 2.071.84 3.946 2.197 5.303a7.477 7.477 0 0 0 7.542 1.852c.892-.282 1.313-.427 1.676-.336.364.091.67.418 1.33 1.079l.805.803.804.805c.663.662.994.994 1.326.994.331 0 .663-.332 1.326-.994.662-.663.994-.995.994-1.326 0-.332-.332-.663-.994-1.326zM10.5 15.75a5.233 5.233 0 0 1-3.712-1.538A5.234 5.234 0 0 1 5.25 10.5c0-1.45.588-2.762 1.538-3.712A5.234 5.234 0 0 1 10.5 5.25c1.45 0 2.762.588 3.712 1.538A5.234 5.234 0 0 1 15.75 10.5c0 1.45-.588 2.762-1.538 3.712A5.234 5.234 0 0 1 10.5 15.75z">
                </path>
              </svg></div>
          </div><input type="search" aria-label="[object Object]" autocomplete="off" name="q" placeholder="Kreative suchen" class="sc-eJwWfJ hkIfQt" value="">
        </div>
      </div>
    </div>
  </div>
</form>

Text Content

Stable WarpFusion v0.15 - alpha masked diffusion - Download | Patreon
Skip navigation
 * Anmelden
 * 
 * 


 * 
 * Auf Patreon durchstarten
 * Anmelden


Mitglied werden




SXELA


Stable WarpFusion v0.15 - alpha masked diffusion - Download

6. Juni

Sort of a disclaimer: only nvidia gpu with 8gb+ or hosted env

don't dive headfirst into a nightly build if you're planning to use it for your
currect project, which is already past its deadline - you'll have a bad day.
This is not a production-ready user-friendly software :D

Make sure you've tried awesome free solutions like Deforum or TemporalKit before
subscribing and submitting yourself to the warp.

Hope you like the current development shpeed. You can't stop me now :D

New:

 * add alpha masked diffusion
 * add inverse alpha mask diffusion
 * save settings to exif
 * backup existing settings on resume run
 * load settings from png exif
 * add beep
 * move consistency mask dilation to render settings
 * hide edge width/dilation from generate flow cell

upd 8.6.23 v0.15.1:

 * add pattern replacement (filtering) for prompt
 * fix constant bitrate error during video export causing noise in high-res
   videos

v0.15.2:

 * fix typo in cell 1.5

v0.15.3:

 * fix full-screen consistency mask error (also bumped missed consistency
   dilation to 2)

12.06.2023: bumped to nightly.

v0.15.4:

 * fix keep_audio not working for relative video path thanks to louis.jeck#2502

26.6.2023

 * fix consistency error between identical frames

More about that bug here -
https://discord.com/channels/973802253204996116/1122765734532087889

5.7.2023

 * fix torchmetrics version thx to tomatoslasher

this one - ImportError: cannot import name '_compare_version' from
'torchmetrics.utilities.imports'
(/usr/local/lib/python3.10/dist-packages/torchmetrics/utilities/imports.py)

13.08.2023:
Moved to M tier





ALPHA MASKED DIFFUSION

Same as masked diffusion, which was using consistency mask before, but this time
it uses alpha mask. masked_diffusion has been renamed to cc_masked_diffusion.

It works this way:

if current diffusion step is before the masked_diffusion values, both masks are
used, and their masked areas (black) are being diffused, unmasked (white) are
being fixed.

if current diffusion step is between the masked_diffusion values, the rightmost
mask (the one with the higher masked_diffusion value) is used.

if current diffusion step is above the masked_diffusion values, the whole frame
is diffused.


BEEP

Check Beep to beep. Useful to signal when the render is over.


SAVE & LOAD SETTINGS UPDATE

Settings are now saved to frame exif data. You can load them from the frame by
specifying a path to it instead of a txt file.

If you are changing your settings during resume run, it will backup existing
settings.txt, which were lost before.


PATTERN REPLACEMENT (PROMPT FILTER)

You can now automatically replace certain word or phrases.

For example, you can have a lot of animated scene descriptions across numerous
frames but want to test different styles. You can set a keyword {style} smewhere
in your prompt and replace it with the whole new style without touching your
prompts at all to iterate quickly.

It works like this:
go to GUI - Replace patterns and use the following notation:
{0: {"keyword or phrase": "replacement"}}

it can also be scheduled:
{0: {"keyword or phrase": "replacement"}, 10:{"another keyword or phrase":
"another replacement"}}

This will replace "keyword or phrase" with "replacement" at frame 0 and "another
keyword or phrase" with "another replacement" at frame 10.

You can use multiple filters per frame:

{0: {"keyword or phrase": "replacement", "another keyword or phrase": "another
replacement"}


This is applied after captions, so you can use that to filter unnecessary words,
for example "cat" if you already have that in your prompt, or want to replace
"cat" with "dog" in your captions.


stable_warpfusion_v0_15_7.ipynb

changelog

download

25


82




Weitere Kommentare laden
Jatinder singh
3 M.

15.4 file link,15.6 out of mmry problem,reclnty deleted evrything


Sxela
3 M.

ok


Jatinder singh
3 M.

❤️❤️❤️❤️thanks sir for 15.4 version

1


Almila Duru Kavak
3 M.

hi, can you share settings txt file for gui? I need to set more settings for
prompt.


Sxela
3 M.

Hi, you can open any video on my YouTube and check its settings in the
description


su jackson
3 M.

Hi, I encounter some issue and I tried install, !python -m pip -q install
guided_diffusion ERROR: Could not find a version that satisfies the requirement
guided_diffusion (from versions: none) ERROR: No matching distribution found for
guided_diffusion

1


Sxela
3 M.

Interesting. What os are you using?


Felipe Mandiola
2 M.

I have encountered an issue. When trying to run the file following a tutorial a
"ModuleNotFoundError: No module named 'timm'" keeps popping up.


Sxela
2 M.

uncheck skip install, restart and run all


Arthur Valter
2 M.

Hi, I followed all the steps carefully but the render stops at 1.4 / -> 12
import timm, I can’t find any solution to my problem, I've tried again but I
have the same problem, can someone help me about it ?


Sxela
2 M.

Hi, please check this post -
https://www.patreon.com/posts/if-youre-getting-86836721

1

Antworten laden
Thinh Nguyen
2 M.

KeyboardInterrupt Traceback (most recent call last) in () 19 output.eval_js('new
Audio("https://upload.wikimedia.org/wikipedia/commons/0/05/Beep-09.ogg").play()')
20 ---> 21 raise KeyboardInterrupt KeyboardInterrupt:


Sxela
2 M.

You have interrupted the run manually


Thinh Nguyen
2 M.

help :3


Abhishek Bera
2 M.

I am using windows but have 4 gigs of CUDA, i have a pickle file for my model,
is there anyway to get rid of memory error even if it is slower to render?


Sxela
2 M.

4gb is below the recommended 8gb amount, you can try 512x512 with v1

1

Matt Jenkins
1 M.

Any ideas what to do about this Runtimerror I'm getting? RuntimeError Traceback
(most recent call last) in () 492 smallpath = None 493 config =
OmegaConf.load(f"{root_dir}/ControlNet/models/cldm_v15.yaml") --> 494 sd_model =
load_model_from_config(config=config, 495 ckpt=model_path, vae_ckpt=vae_ckpt,
#controlnet=smallpath, 496 verbose=True) 1 frames
/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py in
load_state_dict(self, state_dict, strict) 2039 2040 if len(error_msgs) > 0: ->
2041 raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
2042 self.__class__.__name__, "\n\t".join(error_msgs))) 2043 return
_IncompatibleKeys(missing_keys, unexpected_keys) RuntimeError: Error(s) in
loading state_dict for ControlLDM: size mismatch for
model.diffusion_model.input_blocks.1.1.proj_in.weight: copying a param with
shape


Sxela
1 M.

Hi, make sure model_version/model checkpoint are compatible i.e. you use v1 file
for v1 version and so on

1




WERDE MITGLIED VON

70
Schalte 70 exklusive Posts frei

Werde Teil der Community

Tausche dich über private Nachrichten mit dem/der Kreativen aus
Sxela
creating stuff using AI in an unintended way.

Mitglied werden

LEVEL

GROUPAI

1 $ pro Monat

You just want to chip in, tip your hat, or nod in my general direction, but not
ready to dive headfirst into the world of warp.

This is a sort of your Patreon read later bookmark.

Doesn't give any benefits or access to non-public posts or notebooks.



Versions available: 0.15 (public)

 * 
   General Support

Zum Level für 1 $ wechseln


DERP LEARNING - M

5 $ pro Monat

You are awesome! You like what I'm doing and want to support me in my
experiments, so I can keep messing around in the name of science (or not) You
get your hands on my stuff before it goes public, and behind-the-scenes goodies
of the stuff I create.



3 versions behind L tier. Latest version available to this tier: v0.20



 * This is not a paid service, tech support service, or anything like that. I
   make these notebooks for myself and share them here. I do my best to provide
   support and guidance, but it may get pretty crowded, so dm or tag me.

 * Doesn't work on Mac or an AMD GPU.

 * This is not a production-ready software with one button to get a cool result
   or something. It has a steep learning curve and you might fail a lot.

 * You will need an Nvidia GPU with at least 8GB VRAM and 16Gb system RAM (local
   or hosted/colab)



If you've spent more than a few hours and couldn't get it to run, please join
our discord server and post your error screenshot in the tech support channel,
that's perfectly fine.


Mit Discord-Benefits
 * 
   Early access

Zum Level für 5 $ wechseln


DERP LEARNING - L

10 $ pro Monat

You are 2x as awesome! You like what I'm doing and want to support me in my
experiments, so I can keep messing around in the name of science (or not)

You are tech-savvy and not afraid to touch THE CODE. You'll get to get your
hands dirty with the nightly builds of new features just as they're being added
and are more or less working :D



Latest version available to this tier: v0.23



 * This is not a paid service, tech support service, or anything like that. I
   make these notebooks for myself and share them here. I do my best to provide
   support and guidance, but it may get pretty crowded, so dm or tag me.

 * Doesn't work on Mac or an AMD GPU.

 * This is not a production-ready software with one button to get a cool result
   or something. It has a steep learning curve and you might fail a lot.

 * You will need an Nvidia GPU with at least 8GB VRAM and 16Gb system RAM (local
   or hosted/colab)



If you've spent more than a few hours and couldn't get it to run, please join
our discord server and post your error screenshot in the tech support channel,
that's perfectly fine.


Mit Discord-Benefits
 * 
   Early access

Zum Level für 10 $ wechseln


DERP LEARNING - XL

25 $ pro Monat

You are 25x as awesome! You like what I'm doing and want to support me in my
experiments, so I can keep messing around in the name of science (or not) You
get your hands on my stuff before it goes public, and behind-the-scenes goodies
of the stuff I create. You are also getting the most unstable and buggy preview
versions, before they go to the nightly.



Your name will be added to the monthly release credits (unless you explicitly
ask me not to do It, of course)



 * This is not a paid service, tech support service, or anything like that. I
   make these notebooks for myself and share them here. I do my best to provide
   support and guidance, but it may get pretty crowded, so dm or tag me.

 * Doesn't work on Mac or an AMD GPU.

 * This is not a production-ready software with one button to get a cool result
   or something. It has a steep learning curve and you might fail a lot.

 * You will need an Nvidia GPU with at least 8GB VRAM and 16Gb system RAM (local
   or hosted/colab)



If you've spent more than a few hours and couldn't get it to run, please join
our discord server and post your error screenshot in the tech support channel,
that's perfectly fine.


Mit Discord-Benefits
 * 
   Early access
 * 
   Exclusive content
 * 
   Patron shout-out in the notebook

Zum Level für 25 $ wechseln


Weitere Level anzeigen

NEUE POSTS

 * Aa
   WarpAiBot: AI-powered tech support bot for discord
   15. September um 18:08
 * Aa
   If you're getting ModuleNotFound: safetensors error
   24. August um 01:02
 * Aa
   If you're getting black frames
   21. August um 08:51
 * Aa
   Stable WarpFusion v0.14 - bugfixes and tweaks - Nightly - Download
   29. Mai um 13:04
 * Stable WarpFusion v0.13 Nightly - New consistency algo, Reference CN
   (changelog)
   26. Mai um 18:42


Sprache: Deutsch
Währung: EUR
 * Über uns
 * Karriere
 * Auf Patreon durchstarten
 * Marke
 * Presse
 * Partner
 * Sitemap

 * Hilfe & FAQ
 * Entwickler*innen
 * App-Verzeichnis
 * Blog
 * Patreon U | Coaching für Kreative
 * Community-Richtlinien
 * Nutzungsbedingungen
 * Datenschutzrichtlinie
 * Datenschutzeinstellungen
 * Bedienhilfen


© Patreon
600 Townsend Street, Suite 500
San Francisco, CA 94103
USA
Telefonnummer: +1 (833) 972-8766